R Notebook

#loading the necessary packages
library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.3.1 ──
✔ ggplot2 3.3.6     ✔ purrr   0.3.4
✔ tibble  3.1.7     ✔ dplyr   1.0.9
✔ tidyr   1.2.0     ✔ stringr 1.4.0
✔ readr   2.1.2     ✔ forcats 0.5.1
Warning: package ‘ggplot2’ was built under R version 4.2.1Warning: package ‘dplyr’ was built under R version 4.2.1── Conflicts ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

library(janitor)

Warning: package ‘janitor’ was built under R version 4.2.1
Attaching package: ‘janitor’

The following objects are masked from ‘package:stats’:

    chisq.test, fisher.test

library(readxl)

Warning: package ‘readxl’ was built under R version 4.2.1

library(here)

Warning: package ‘here’ was built under R version 4.2.1here() starts at C:/Users/nico-/OneDrive/Desktop/Codeclan/dirty_data_project/dirty_data_project/task_4/dirty_data_task_4

#loading the data
candy_2015 <- read_excel(here("../raw_data/boing-boing-candy-2015.xlsx")) %>% 
  clean_names()
candy_2016 <- read_excel(here("../raw_data/boing-boing-candy-2016.xlsx")) %>% 
  clean_names()
candy_2017 <- read_excel(here("../raw_data/boing-boing-candy-2017.xlsx")) %>% 
  clean_names()

New names:

candy_2016

candy_2015

candy_2017

#order of operations: #decide which variables to keep for the analysis according to business questions # Pivot data the same for all 3 datasets # perform pivot on all three # Investigate other columns

#keeping variables useful for analysis from 2015 dataset #The variables are a bit confusing. I will only keep only variables that are actual food and drop anything which is not food.

candy_2015 <- candy_2015 %>% 
  select(-c(
    cash_or_other_forms_of_legal_tender, 
    creepy_religious_comics_chick_tracts, 
    hugs_actual_physical_hugs, 
    please_leave_any_remarks_or_comments_regarding_your_choices: 
    please_estimate_the_degrees_of_separation_you_have_from_the_following_folks_beyonce_knowles, 
    dental_paraphenalia, 
    generic_brand_acetaminophen, 
    peterson_brand_sidewalk_chalk
))
candy_2015

#time to rename some columns. Maybe not that necessary but I would like to have my final results with neat names.

candy_2015 <- candy_2015 %>% 
  rename("trick_or_treat" = are_you_going_actually_going_trick_or_treating_yourself,
         "grand_bar" = x100_grand_bar, 
         "brown_globs" = anonymous_brown_globs_that_come_in_black_and_orange_wrappers, 
         "any_candy_bar" = any_full_sized_candy_bar, 
         "brach_without_candy_corn" = brach_products_not_including_candy_corn, 
         "high_fructose_corn_syrup" = vials_of_pure_high_fructose_corn_syrup_for_main_lining_into_your_vein, 
         "restaurant_candy" = candy_that_is_clearly_just_the_stuff_given_out_for_free_at_restaurants, 
         "chick_o_sticks"  = chick_o_sticks_we_don_t_know_what_that_is, 
         "old_marshmallow" = those_odd_marshmallow_circus_peanut_things)
candy_2015

#same thing for the 2016 dataset

#selecting only the necessary columns for final analysis
candy_2016 <- candy_2016 %>% 
  select(-c(cash_or_other_forms_of_legal_tender, 
            creepy_religious_comics_chick_tracts, 
            dental_paraphenalia, 
            generic_brand_acetaminophen, 
            hugs_actual_physical_hugs, 
            person_of_interest_season_3_dvd_box_set_not_including_disc_4_with_hilarious_outtakes, 
            sourpatch_kids_i_e_abominations_of_nature, 
            vials_of_pure_high_fructose_corn_syrup_for_main_lining_into_your_vein, 
            please_list_any_items_not_included_above_that_give_you_joy:
              york_peppermint_patties_ignore))
candy_2016

candy_2016 <- candy_2016 %>% 
  rename("trick_or_treat" = are_you_going_actually_going_trick_or_treating_yourself, 
         "gender" = your_gender, 
         "age" = how_old_are_you, 
         "country" = which_country_do_you_live_in, 
         "state_province" = which_state_province_county_do_you_live_in, 
         "grand_bar" = x100_grand_bar, 
         "brown_globs" = anonymous_brown_globs_that_come_in_black_and_orange_wrappers, 
         )
candy_2016

#sorting the country column